Deploy MCP server to Fly.io with state tracking, locks, and health checks. DO NOT use ssh_exec for deployments - always use this tool instead.
AI agents invoke deploy_mcp_server to trigger actions in Last Rock MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes infrastructure deployment operations on a remote platform (Fly.io), which is an irreversible operational action that affects live systems. While not destructive in the data-deletion sense, deployment triggers external execution with significant blast radius: misconfigured deployments could take down services, expose secrets, or corrupt application state.
From the tool's definition Tool description states it "Deploy[s] MCP server to Fly.io" with "state tracking, locks, and health checks." The emphasis "DO NOT use ssh_exec for deployments - always use this tool instead" indicates this triggers external operations (deployment to Fly.io)…
Attacks that exploit this kind of access
Deploy MCP server to Fly.io with state tracking, locks, and health checks. DO NOT use ssh_exec for deployments - always use this tool instead. It is categorised as a Execute tool in the Last Rock MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Last Rock MCP server in PolicyLayer and add a rule for deploy_mcp_server: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Last Rock MCP. Nothing to install.
deploy_mcp_server is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the deploy_mcp_server rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for deploy_mcp_server. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
deploy_mcp_server is provided by the Last Rock MCP server (itsablabla/lastrock-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →